CN113779886A - Method, device and system for detecting welding spot quality abnormity based on deep learning - Google Patents
Method, device and system for detecting welding spot quality abnormity based on deep learning Download PDFInfo
- Publication number
- CN113779886A CN113779886A CN202111098723.6A CN202111098723A CN113779886A CN 113779886 A CN113779886 A CN 113779886A CN 202111098723 A CN202111098723 A CN 202111098723A CN 113779886 A CN113779886 A CN 113779886A
- Authority
- CN
- China
- Prior art keywords
- welding
- parameters
- dynamic
- simulation
- dynamic welding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K11/00—Resistance welding; Severing by resistance heating
- B23K11/10—Spot welding; Stitch welding
- B23K11/11—Spot welding
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K11/00—Resistance welding; Severing by resistance heating
- B23K11/24—Electric supply or control circuits therefor
- B23K11/25—Monitoring devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/006—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to using of neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K31/00—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups
- B23K31/12—Processes relevant to this subclass, specially adapted for particular articles or purposes, but not covered by only one of the preceding main groups relating to investigating the properties, e.g. the weldability, of materials
- B23K31/125—Weld quality monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The application relates to a method, a device and a system for detecting welding spot quality abnormity based on deep learning, wherein the method comprises the following steps: the method comprises the steps of obtaining dynamic welding parameters in a welding process corresponding to any target welding point, inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, obtaining welding simulation parameters output by the dynamic welding parameter simulation model, determining errors between the dynamic welding parameters and the welding simulation parameters, and determining the target welding point as an abnormal welding point under the condition that the errors are larger than a preset threshold value. Based on this, the scheme of this application breaks away from artifical chiseling to detect the abnormality and carry out the batchization, the speed that detects the abnormality is faster, can cover all solder joints.
Description
Technical Field
The application relates to the technical field of welding quality detection, in particular to a method, a device and a system for detecting welding spot quality abnormity based on deep learning.
Background
Resistance welding has characteristics of low cost, high efficiency, and strong adaptability, and thus, resistance welding may be applied to a production scenario of mass production. In a mass production scenario, a large number of welding spots are formed by resistance welding, such as a body-in-white welding of an automobile, which may have more than about 4000 welding spots, and the quality inspection commonly used at present basically inspects the quality of the resistance welding by sampling and manually chiseling.
However, the manual drilling method of sampling can not cover all the welding points, and the manual drilling method needs manual operation and takes a long time, so that the detection cost is high.
Disclosure of Invention
In order to solve the problems that all welding spots cannot be covered, manual operation is needed, time consumption is long, and detection cost is high in the related technology, the application provides a welding spot quality abnormity detection method, device and system based on deep learning.
According to a first aspect of the application, a method for detecting weld spot quality abnormality based on deep learning is provided, which includes:
acquiring dynamic welding parameters in a welding process corresponding to any target welding point;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring welding simulation parameters output by the dynamic welding parameter simulation model;
and determining the error between the dynamic welding parameters and the welding simulation parameters, and determining the target welding spot as an abnormal welding spot under the condition that the error is greater than a preset threshold value.
In an alternative embodiment, the dynamic welding parameter simulation model is a deep learning auto-encoder model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained deep learning automatic encoder model to reconstruct the dynamic welding parameters, and acquiring welding simulation parameters output by the automatic encoder model.
In an optional embodiment, the inputting the dynamic welding parameters into a pre-trained deep learning automatic encoder model to reconstruct the dynamic welding parameters, and obtaining the welding simulation parameters output by the automatic encoder model, includes:
inputting the dynamic welding parameters into an encoder layer of a pre-trained deep learning automatic encoder model for dimensionality reduction mapping, and acquiring target dimensionality parameters output by the encoder layer;
and inputting the target dimension parameters into a decoder layer of a pre-trained deep learning automatic encoder model for reconstruction mapping, and acquiring welding simulation parameters output by the decoder layer.
In an alternative embodiment, the dynamic welding parameter simulation model is a sequence-to-sequence model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained sequence-to-sequence model to predict the dynamic welding parameters, and acquiring welding simulation parameters output by the sequence-to-sequence model.
In an optional embodiment, the acquiring a dynamic welding parameter in a welding process corresponding to any target welding point includes:
and under the condition of welding any target welding point, acquiring dynamic welding parameters in the welding process at preset time intervals.
In an optional embodiment, the method further comprises:
if the error is smaller than or equal to a preset threshold value, storing the obtained dynamic welding parameters of the target welding spot into a target storage area;
and acquiring the stored dynamic welding parameters from the target storage area, and performing update training on the dynamic welding parameter simulation model by taking the stored dynamic welding parameters as training samples.
In an optional embodiment, the performing update training on the dynamic welding parameter simulation model by using the stored dynamic welding parameters as training samples includes:
for any group of training samples, inputting the training samples into the dynamic welding parameter simulation model for simulation, and acquiring simulation sample data output by the dynamic welding parameter simulation model;
and adjusting the model parameters of the dynamic welding parameter simulation model according to the error between the simulation sample data and the training sample so as to realize the update training of the dynamic welding parameter simulation model.
According to a second aspect of the present application, there is provided a solder joint quality abnormality detection apparatus based on deep learning, the apparatus including:
the acquisition module is used for acquiring dynamic welding parameters in the welding process corresponding to any target welding point;
the simulation module is used for inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters and acquiring welding simulation parameters output by the dynamic welding parameter simulation model;
and the abnormity judging module is used for determining the error between the dynamic welding parameter and the welding simulation parameter, and determining the target welding spot as an abnormal welding spot under the condition that the error is greater than a preset threshold value.
According to a third aspect of the application, a welding spot quality abnormity detection system based on deep learning is provided, and the system comprises a dynamic welding parameter acquisition device, a welding spot quality abnormity detection device and a welding spot data display control device;
the dynamic welding parameter acquisition equipment is used for acquiring dynamic welding parameters of the welding equipment in the process of welding a target welding spot and sending the dynamic welding parameters to the welding spot data display control equipment;
the welding spot quality abnormity detection equipment is connected with the welding spot data display control equipment and is used for receiving dynamic welding parameters sent by the welding spot data display control equipment and determining whether the target welding spot is an abnormal welding spot according to the dynamic welding parameters according to the method of the first aspect of the application;
and the welding spot data display control equipment is used for displaying the dynamic welding parameters and sending the dynamic welding parameters to the welding spot quality abnormity detection equipment.
According to a fourth aspect of the present application, there is provided a storage medium storing one or more programs which, when executed, implement the method of the first aspect of the present application.
The technical scheme provided by the application can comprise the following beneficial effects: the method comprises the steps of obtaining dynamic welding parameters in a welding process corresponding to any target welding point, inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, obtaining welding simulation parameters output by the dynamic welding parameter simulation model, determining errors between the dynamic welding parameters and the welding simulation parameters, and determining the target welding point as an abnormal welding point under the condition that the errors are larger than a preset threshold value. The dynamic welding parameters in the welding process can directly reflect the quality of welding, so that a pre-trained dynamic welding parameter simulation model is utilized to simulate according to the obtained dynamic welding parameters to obtain welding simulation parameters, if the error between the dynamic welding parameters and the welding simulation parameters is larger than a preset threshold value, the welding process corresponding to the dynamic welding parameters is indicated, and target welding spots obtained by welding are abnormal welding spots.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic flowchart illustrating a method for detecting weld spot quality abnormality based on deep learning according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a deep learning-based solder joint quality anomaly detection apparatus according to another embodiment of the present application;
FIG. 3 is a schematic structural diagram of a deep learning-based weld spot quality anomaly detection system according to another embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a method for detecting weld spot quality abnormality based on deep learning according to an embodiment of the present disclosure.
As shown in fig. 1, the method for detecting weld spot quality abnormality based on deep learning according to this embodiment may include:
and S101, acquiring dynamic welding parameters in the welding process corresponding to any target welding point.
In this step, the main body for implementing the welding process may be a welding robot, a welding machine tool, etc., and the dynamic welding parameters corresponding to different main bodies may be different, for example, the welding robot installs a welding clamp on an arm of the welding robot, and sets a welding controller for controlling the welding process. In the case of welding any target welding point, the dynamic welding parameters in the welding process are obtained at preset time intervals, and specifically, the dynamic welding parameters may include welding current, welding voltage, resistance, and power.
In one particular example, the welding controller may control the current during the welding process in different ways, such as a constant phase angle, constant current, or adaptive, where a constant phase angle refers to a fixed value of on time per welding cycle; constant current means that the welding controller ensures constant welding current regardless of changes in load and power supply; adaptive means that the electrical characteristics of the material change according to the mechanical characteristics of the material during welding, and the welding controller adjusts the control current according to the change.
No matter what control mode, after welding electrification is completed, the welding controller records the change of welding current in the process, calculates the root mean square value of the change, and then takes all current values and the calculated root mean square value of the change as the welding current in the dynamic welding parameters.
In addition, for the welding voltage, a voltage detection line can be arranged on the welding tongs to collect the welding voltage in the welding process, wherein the welding voltage comprises the voltage value formed by the basically unchanged welding tongs voltage and the welding core resistance which is changed all the time, the welding controller records the change of the voltage in the process after the welding electrification is finished and calculates the root mean square value of the change, and then all the voltage values and the calculated root mean square value of the voltage are used as the welding voltage in the dynamic welding parameters.
For resistance, the resistance can be calculated using the collected welding voltage and welding current. Specifically, a resistance value can be calculated from the welding voltage and the welding current detected at the same time, then the welding controller records the change of the resistance in the process after the welding power-on is completed and calculates the root mean square value of the resistance, and then all the resistance values and the calculated root mean square value of the resistance are used as the resistance in the dynamic welding parameters.
For power, the power may be calculated using the collected welding voltage and welding current. Specifically, a power value can be calculated from the welding voltage and the welding current detected at the same time, then the welding controller records the change of the power in the process after the welding is electrified and calculates the root mean square value of the change, and then all the power values and the calculated root mean square value of the power are used as the power in the dynamic welding parameters.
It should be noted that the aforementioned preset time duration may be in milliseconds, and the acquired dynamic welding parameters may form a welding process curve with time as a first axis and the dynamic welding parameters as a second axis. Wherein each target weld point forms a weld process curve. This curve may be more conducive to the simulation of dynamic welding parameters by the following steps.
And S102, inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring welding simulation parameters output by the dynamic welding parameter simulation model.
In this step, the dynamic welding parameter simulation model is a model for obtaining a set of welding simulation parameters through simulation according to actual dynamic welding parameters, and the simulation mode can be various, such as parameter reconstruction and parameter prediction.
Specifically, the dynamic welding parameter simulation model may be a deep learning automatic encoder model, and the dynamic welding parameters are input into a pre-trained deep learning automatic encoder model to be reconstructed, and the deep learning automatic encoder model may output the welding simulation parameters, and at this time, the welding simulation parameters output by the deep learning automatic encoder model are directly obtained.
The deep learning automatic encoder model can be provided with an encoder layer and a decoder layer, specifically, can input the dynamic welding parameter book into the encoder layer of the deep learning automatic encoder model trained in advance, carries out dimensionality reduction mapping on the dynamic welding parameters to obtain target dimensionality parameters, directly obtains the target dimensionality parameters output by the encoder layer, then inputs the target dimensionality parameters into the decoder layer of the deep learning automatic encoder model trained in advance to carry out reconstruction mapping, and obtains the target dimensionality parameters output by the decoder layer.
It should be noted that the deep learning automatic encoder model can be trained by using a large number of dynamic welding parameters of normal welding points, so that the model learns the dynamic welding parameter encoding and decoding rules of the normal welding points. During specific training, the difference between the minimized welding simulation parameter and the input dynamic welding parameter can be used as a target for training.
In addition, the dynamic welding parameter simulation model may also be a sequence-to-sequence model, specifically, the dynamic welding parameters may be input into a sequence-to-sequence model trained in advance, the dynamic welding parameters may be predicted, and then the welding simulation parameters output by the sequence-to-sequence model may be acquired.
Generally, the dynamic welding parameter process curve of the normal welding point formed in the previous input step can be used as the dynamic welding parameter and input into the sequence-to-sequence model, and the sequence-to-sequence model is trained by still using the minimized difference between the input and the output as the training target.
It should be noted that, whether it is an automatic encoder model or a sequence-to-sequence model, it can be constructed by a Convolutional Neural Network (CNN), a cyclic neural network (RNN), a long-term memory network (LSTM), and a modified gru (gate recovery unit) of the RNN.
Step S103, determining an error between the dynamic welding parameter and the welding simulation parameter, and determining the target welding point as an abnormal welding point under the condition that the error is greater than a preset threshold value.
In this step, the preset threshold may be set according to the welding experiment and the simulation result of the dynamic welding parameter simulation model.
Because the dynamic welding parameter simulation model is trained by taking the dynamic welding parameters of a large number of normal welding points as training samples and taking minimized input and output as training purposes, the welding simulation parameters output by the dynamic welding parameter simulation model are very close to the dynamic welding parameters in the face of the normal welding points, and the error is smaller than a preset threshold value; when an abnormal welding spot is faced, the welding simulation parameter output by the dynamic welding parameter simulation model is closer to the dynamic welding parameter when the abnormal welding spot is welded to a normal welding spot, and the error between the welding simulation parameter and the collected dynamic welding parameter is larger than a preset threshold value.
Therefore, the scheme of the application can judge whether the target welding spot is an abnormal welding spot by using the dynamic welding parameters.
In order to keep the accuracy of the dynamic welding parameter simulation model high, the dynamic welding parameter simulation model can be trained in real time in the detection process. Specifically, if the error is smaller than or equal to a preset threshold, storing the acquired dynamic welding parameters of the target welding spot into a target storage area; and acquiring the stored dynamic welding parameters from the target storage area, and performing update training on the dynamic welding parameter simulation model by taking the stored dynamic welding parameters as training samples.
In this embodiment, for any group of training samples, the training samples may be input to the dynamic welding parameter simulation model for simulation, and simulation sample data output by the dynamic welding parameter simulation model is obtained; and adjusting the model parameters of the dynamic welding parameter simulation model according to the error between the simulation sample data and the training sample so as to realize the update training of the dynamic welding parameter simulation model.
In the embodiment, a dynamic welding parameter in a welding process corresponding to any target welding point is obtained, the dynamic welding parameter is input into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameter, the welding simulation parameter output by the dynamic welding parameter simulation model is obtained, an error between the dynamic welding parameter and the welding simulation parameter is determined, and the target welding point is determined to be an abnormal welding point under the condition that the error is greater than a preset threshold value. The dynamic welding parameters in the welding process can directly reflect the quality of welding, so that a pre-trained dynamic welding parameter simulation model is utilized to simulate according to the obtained dynamic welding parameters to obtain welding simulation parameters, if the error between the dynamic welding parameters and the welding simulation parameters is larger than a preset threshold value, the welding process corresponding to the dynamic welding parameters is indicated, and target welding spots obtained by welding are abnormal welding spots.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a welding spot quality abnormality detection apparatus based on deep learning according to another embodiment of the present disclosure.
As shown in fig. 2, the apparatus for detecting quality abnormality of a weld spot based on deep learning provided by the present embodiment may include:
an obtaining module 201, configured to obtain a dynamic welding parameter in a welding process corresponding to any target welding point;
the simulation module 202 is configured to input the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and obtain welding simulation parameters output by the dynamic welding parameter simulation model;
and the abnormity determining module 203 is configured to determine an error between the dynamic welding parameter and the welding simulation parameter, and determine that the target welding point is an abnormal welding point when the error is greater than a preset threshold value.
In this embodiment, the obtaining module 201 obtains a dynamic welding parameter in a welding process corresponding to any target welding point, the simulation module 202 inputs the dynamic welding parameter into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameter and obtains a welding simulation parameter output by the dynamic welding parameter simulation model, the abnormality determining module 203 determines an error between the dynamic welding parameter and the welding simulation parameter, and determines the target welding point as an abnormal welding point when the error is greater than a preset threshold. The dynamic welding parameters in the welding process can directly reflect the quality of welding, so that a pre-trained dynamic welding parameter simulation model is utilized to simulate according to the obtained dynamic welding parameters to obtain welding simulation parameters, if the error between the dynamic welding parameters and the welding simulation parameters is larger than a preset threshold value, the welding process corresponding to the dynamic welding parameters is indicated, and target welding spots obtained by welding are abnormal welding spots.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a system for detecting quality abnormality of a solder joint based on deep learning according to another embodiment of the present disclosure.
As shown in fig. 3, the welding spot quality abnormality detection system based on deep learning provided in this embodiment may include a dynamic welding parameter acquisition device 301, a welding spot quality abnormality detection device 302, and a welding spot data display control device 303;
the dynamic welding parameter acquisition equipment is used for acquiring dynamic welding parameters in the process of welding a target welding point by the welding equipment 304 and sending the dynamic welding parameters to the welding point data display control equipment;
the welding spot quality abnormity detection equipment is connected with the welding spot data display control equipment and is used for receiving dynamic welding parameters sent by the welding spot data display control equipment and determining whether the target welding spot is an abnormal welding spot according to the dynamic welding parameters by the method provided by the embodiment of the method;
and the welding spot data display control equipment is used for displaying the dynamic welding parameters and sending the dynamic welding parameters to the welding spot quality abnormity detection equipment.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to another embodiment of the present application.
As shown in fig. 4, the electronic device provided in this embodiment includes: at least one processor 401, memory 402, at least one network interface 403, and other user interfaces 404. The various components in the electronic device 400 are coupled together by a bus system 405. It is understood that the bus system 405 is used to enable connection communication between these components. The bus system 405 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 405 in fig. 4.
The user interface 404 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, touch pad, or touch screen, among others.
It will be appreciated that memory 402 in embodiments of the invention may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of illustration and not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (ddr Data Rate SDRAM, ddr SDRAM), Enhanced Synchronous SDRAM (ESDRAM), synchlronous SDRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 402 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some embodiments, memory 402 stores the following elements, executable units or data structures, or a subset thereof, or an expanded set thereof: an operating system 4021 and a second application 4022.
The operating system 4021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is configured to implement various basic services and process hardware-based tasks. The second application 4022 includes various second applications, such as a Media Player (Media Player), a Browser (Browser), and the like, for implementing various application services. A program for implementing the method according to an embodiment of the present invention may be included in the second application 4022.
In the embodiment of the present invention, the processor 401 is configured to execute the method steps provided by the method embodiments by calling a program or an instruction stored in the memory 402, specifically, a program or an instruction stored in the second application 4022.
The method disclosed in the above embodiments of the present invention may be applied to the processor 401, or implemented by the processor 401. The processor 401 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 401. The Processor 401 may be a general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 402, and the processor 401 reads the information in the memory 402 and completes the steps of the method in combination with the hardware.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or any combination thereof. For a hardware implementation, the Processing units may be implemented in one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), general purpose processors, controllers, micro-controllers, microprocessors, other electronic units configured to perform the functions of the present Application, or a combination thereof.
For a software implementation, the techniques herein may be implemented by means of units performing the functions herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The embodiment of the invention also provides a storage medium (computer readable storage medium). The storage medium herein stores one or more programs. Among others, the storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
When the one or more programs in the storage medium are executable by the one or more processors, the method for detecting weld spot quality abnormality based on deep learning performed on the electronic device side is realized.
The processor is used for executing a deep learning-based welding spot quality abnormity detection program stored in the memory so as to realize the following steps of the deep learning-based welding spot quality abnormity detection method executed on the electronic equipment side:
acquiring dynamic welding parameters in a welding process corresponding to any target welding point;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring welding simulation parameters output by the dynamic welding parameter simulation model;
and determining the error between the dynamic welding parameters and the welding simulation parameters, and determining the target welding spot as an abnormal welding spot under the condition that the error is greater than a preset threshold value.
In an alternative embodiment, the dynamic welding parameter simulation model is an auto encoder model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained automatic encoder model to reconstruct the dynamic welding parameters, and acquiring welding simulation parameters output by the automatic encoder model.
In an optional embodiment, the inputting the dynamic welding parameters into a pre-trained auto-encoder model to reconstruct the dynamic welding parameters, and obtaining the welding simulation parameters output by the auto-encoder model, includes:
inputting the dynamic welding parameters into an encoder layer of a pre-trained automatic encoder model for dimensionality reduction mapping, and acquiring target dimensionality parameters output by the encoder layer;
and inputting the target dimension parameters into a decoder layer of a pre-trained automatic encoder model for reconstruction mapping, and acquiring welding simulation parameters output by the decoder layer.
In an alternative embodiment, the dynamic welding parameter simulation model is a sequence-to-sequence model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained sequence-to-sequence model to predict the dynamic welding parameters, and acquiring welding simulation parameters output by the sequence-to-sequence model.
In an optional embodiment, the acquiring a dynamic welding parameter in a welding process corresponding to any target welding point includes:
and under the condition of welding any target welding point, acquiring dynamic welding parameters in the welding process at preset time intervals.
In an optional embodiment, the method further comprises:
if the error is smaller than or equal to a preset threshold value, storing the obtained dynamic welding parameters of the target welding spot into a target storage area;
and acquiring the stored dynamic welding parameters from the target storage area, and performing update training on the dynamic welding parameter simulation model by taking the stored dynamic welding parameters as training samples.
In an optional embodiment, the performing update training on the dynamic welding parameter simulation model by using the stored dynamic welding parameters as training samples includes:
for any group of training samples, inputting the training samples into the dynamic welding parameter simulation model for simulation, and acquiring simulation sample data output by the dynamic welding parameter simulation model;
and adjusting the model parameters of the dynamic welding parameter simulation model according to the error between the simulation sample data and the training sample so as to realize the update training of the dynamic welding parameter simulation model.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for detecting welding spot quality abnormity based on deep learning is characterized by comprising the following steps:
acquiring dynamic welding parameters in a welding process corresponding to any target welding point;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring welding simulation parameters output by the dynamic welding parameter simulation model;
and determining the error between the dynamic welding parameters and the welding simulation parameters, and determining the target welding spot as an abnormal welding spot under the condition that the error is greater than a preset threshold value.
2. The method of claim 1, wherein the dynamic welding parameter simulation model is a deep learning auto-encoder model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained deep learning automatic encoder model to reconstruct the dynamic welding parameters, and acquiring welding simulation parameters output by the automatic encoder model.
3. The method of claim 2, wherein the inputting the dynamic welding parameters into a pre-trained deep learning auto-encoder model to reconstruct the dynamic welding parameters to obtain welding simulation parameters output by the auto-encoder model comprises:
inputting the dynamic welding parameters into an encoder layer of a pre-trained deep learning automatic encoder model for dimensionality reduction mapping, and acquiring target dimensionality parameters output by the encoder layer;
and inputting the target dimension parameters into a decoder layer of a pre-trained deep learning automatic encoder model for reconstruction mapping, and acquiring welding simulation parameters output by the decoder layer.
4. The method of claim 1, wherein the dynamic welding parameter simulation model is a sequence-to-sequence model;
inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters, and acquiring the welding simulation parameters output by the dynamic welding parameter simulation model, wherein the welding simulation parameters comprise:
and inputting the dynamic welding parameters into a pre-trained sequence-to-sequence model to predict the dynamic welding parameters, and acquiring welding simulation parameters output by the sequence-to-sequence model.
5. The method according to any one of claims 1 to 4, wherein the obtaining of the dynamic welding parameters in the welding process corresponding to any one target welding point comprises:
and under the condition of welding any target welding point, acquiring dynamic welding parameters in the welding process at preset time intervals.
6. The method of claim 1, further comprising:
if the error is smaller than or equal to a preset threshold value, storing the obtained dynamic welding parameters of the target welding spot into a target storage area;
and acquiring the stored dynamic welding parameters from the target storage area, and performing update training on the dynamic welding parameter simulation model by taking the stored dynamic welding parameters as training samples.
7. The method of claim 6, wherein the updated training of the dynamic welding parameter simulation model using the stored dynamic welding parameters as training samples comprises:
for any group of training samples, inputting the training samples into the dynamic welding parameter simulation model for simulation, and acquiring simulation sample data output by the dynamic welding parameter simulation model;
and adjusting the model parameters of the dynamic welding parameter simulation model according to the error between the simulation sample data and the training sample so as to realize the update training of the dynamic welding parameter simulation model.
8. A solder joint quality anomaly detection device based on deep learning, the device comprising:
the acquisition module is used for acquiring dynamic welding parameters in the welding process corresponding to any target welding point;
the simulation module is used for inputting the dynamic welding parameters into a pre-trained dynamic welding parameter simulation model to simulate the dynamic welding parameters and acquiring welding simulation parameters output by the dynamic welding parameter simulation model;
and the abnormity judging module is used for determining the error between the dynamic welding parameter and the welding simulation parameter, and determining the target welding spot as an abnormal welding spot under the condition that the error is greater than a preset threshold value.
9. A welding spot quality abnormity detection system based on deep learning is characterized by comprising dynamic welding parameter acquisition equipment, welding spot quality abnormity detection equipment and welding spot data display control equipment;
the dynamic welding parameter acquisition equipment is used for acquiring dynamic welding parameters of the welding equipment in the process of welding a target welding spot and sending the dynamic welding parameters to the welding spot data display control equipment;
the welding spot quality abnormity detection equipment is connected with the welding spot data display control equipment and is used for receiving dynamic welding parameters sent by the welding spot data display control equipment and determining whether the target welding spot is an abnormal welding spot according to the dynamic welding parameters by the method of claims 1-7;
and the welding spot data display control equipment is used for displaying the dynamic welding parameters and sending the dynamic welding parameters to the welding spot quality abnormity detection equipment.
10. A storage medium, characterized in that the storage medium stores one or more programs which, when executed, implement the method of any one of claims 1-7.
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098723.6A CN113779886A (en) | 2021-09-18 | 2021-09-18 | Method, device and system for detecting welding spot quality abnormity based on deep learning |
| EP22153260.9A EP4151351A1 (en) | 2021-09-18 | 2022-01-25 | Method, device, and system for detecting welding spot quality abnormalities based on deep learning technical field |
| JP2022010794A JP7381117B2 (en) | 2021-09-18 | 2022-01-27 | Welding quality abnormality detection method, detection device, and detection system based on deep learning |
| US17/677,056 US20230087105A1 (en) | 2021-09-18 | 2022-02-22 | Method, device, and system for detecting welding spot quality abnormalities based on deep learning |
| CN202211129612.1A CN115392132B (en) | 2021-09-18 | 2022-09-16 | Welding spot quality anomaly detection method, device and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111098723.6A CN113779886A (en) | 2021-09-18 | 2021-09-18 | Method, device and system for detecting welding spot quality abnormity based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113779886A true CN113779886A (en) | 2021-12-10 |
Family
ID=78852411
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111098723.6A Pending CN113779886A (en) | 2021-09-18 | 2021-09-18 | Method, device and system for detecting welding spot quality abnormity based on deep learning |
| CN202211129612.1A Active CN115392132B (en) | 2021-09-18 | 2022-09-16 | Welding spot quality anomaly detection method, device and system based on deep learning |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211129612.1A Active CN115392132B (en) | 2021-09-18 | 2022-09-16 | Welding spot quality anomaly detection method, device and system based on deep learning |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230087105A1 (en) |
| EP (1) | EP4151351A1 (en) |
| JP (1) | JP7381117B2 (en) |
| CN (2) | CN113779886A (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116562064B (en) * | 2023-07-11 | 2023-12-12 | 深圳市贝思科尔软件技术有限公司 | Welding test system and method based on simulation model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109714340A (en) * | 2018-12-28 | 2019-05-03 | 厦门服云信息科技有限公司 | The Network Abnormal of a kind of sequence to sequence requests recognition methods and device |
| CN111069736A (en) * | 2019-12-27 | 2020-04-28 | 唐山松下产业机器有限公司 | Storage medium, welding equipment, welding abnormity detection method and device |
| CN111915015A (en) * | 2020-06-30 | 2020-11-10 | 上海金仕达软件科技有限公司 | Abnormal value detection method and device, terminal equipment and storage medium |
| CN113255778A (en) * | 2021-05-28 | 2021-08-13 | 广汽本田汽车有限公司 | Welding spot quality detection method and device based on multi-model fusion and storage medium |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2678190B1 (en) * | 1991-06-28 | 1995-07-07 | Commissariat Energie Atomique | METHOD AND SYSTEM FOR COMPUTER ASSISTED WELDING BASED ON THE VISION OF THE WELDING SCENE. |
| US5450315A (en) * | 1994-09-26 | 1995-09-12 | Square D Company | Apparatus using a neural network for power factor calculation |
| US5764859A (en) * | 1994-10-01 | 1998-06-09 | Orion Metal Company Ltd. | Apparatus for nondestructive on-line inspection of electric resistance welding states and a method thereof |
| US7132617B2 (en) * | 2002-02-20 | 2006-11-07 | Daimlerchrysler Corporation | Method and system for assessing quality of spot welds |
| US8569646B2 (en) * | 2009-11-13 | 2013-10-29 | Lincoln Global, Inc. | Systems, methods, and apparatuses for monitoring weld quality |
| JPWO2012050108A1 (en) * | 2010-10-14 | 2014-02-24 | 新日鐵住金株式会社 | Weld quality discrimination device |
| CN104379291B (en) * | 2012-04-23 | 2016-12-14 | 林肯环球股份有限公司 | For monitoring the system and method for welding quality |
| CN106530284A (en) * | 2016-10-21 | 2017-03-22 | 广州视源电子科技股份有限公司 | Solder joint type detection method and apparatus based on image identification |
| US10695857B2 (en) * | 2017-10-03 | 2020-06-30 | GM Global Technology Operations LLC | Topology-based spot weld optimization with inter-distance constraints |
| US11934183B2 (en) * | 2019-06-13 | 2024-03-19 | Tata Consultancy Services Limited | Method and system for industrial anomaly detection |
| US20210010953A1 (en) * | 2019-07-12 | 2021-01-14 | SVXR, Inc. | Methods and Systems for Defects Detection and Classification Using X-rays |
| CN110434443B (en) * | 2019-07-29 | 2021-05-11 | 中车青岛四方机车车辆股份有限公司 | Resistance spot welding simulation method and system |
| CN112557416A (en) * | 2019-09-09 | 2021-03-26 | 英业达科技有限公司 | System and method for detecting whether welding spots are bridged or not by using deep learning model |
| CN110851338B (en) * | 2019-09-23 | 2022-06-24 | 平安科技（深圳）有限公司 | Abnormality detection method, electronic device, and storage medium |
| TWI783200B (en) * | 2019-12-30 | 2022-11-11 | 緯創資通股份有限公司 | Method and device for determining whether object has defect |
| CN111084621B (en) * | 2019-12-30 | 2022-09-06 | 上海数创医疗科技有限公司 | QRS wave group form identification method and device based on depth self-encoder |
| DE102020202870A1 (en) * | 2020-03-06 | 2021-09-09 | Robert Bosch Gesellschaft mit beschränkter Haftung | Process for validation and selection based on machine learning models for condition monitoring of a machine |
| CN112149757B (en) * | 2020-10-23 | 2022-08-19 | 新华三大数据技术有限公司 | Abnormity detection method and device, electronic equipment and storage medium |
| CN112487708A (en) * | 2020-11-24 | 2021-03-12 | 山西三友和智慧信息技术股份有限公司 | Resistance spot welding quality prediction method based on ensemble learning |
| CN112650146B (en) * | 2020-12-18 | 2021-11-19 | 国家机床质量监督检验中心 | Fault diagnosis optimization method, system and equipment of numerical control machine tool under multiple working conditions |
-
2021
- 2021-09-18 CN CN202111098723.6A patent/CN113779886A/en active Pending
-
2022
- 2022-01-25 EP EP22153260.9A patent/EP4151351A1/en active Pending
- 2022-01-27 JP JP2022010794A patent/JP7381117B2/en active Active
- 2022-02-22 US US17/677,056 patent/US20230087105A1/en active Pending
- 2022-09-16 CN CN202211129612.1A patent/CN115392132B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109714340A (en) * | 2018-12-28 | 2019-05-03 | 厦门服云信息科技有限公司 | The Network Abnormal of a kind of sequence to sequence requests recognition methods and device |
| CN111069736A (en) * | 2019-12-27 | 2020-04-28 | 唐山松下产业机器有限公司 | Storage medium, welding equipment, welding abnormity detection method and device |
| CN111915015A (en) * | 2020-06-30 | 2020-11-10 | 上海金仕达软件科技有限公司 | Abnormal value detection method and device, terminal equipment and storage medium |
| CN113255778A (en) * | 2021-05-28 | 2021-08-13 | 广汽本田汽车有限公司 | Welding spot quality detection method and device based on multi-model fusion and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2023044713A (en) | 2023-03-31 |
| JP7381117B2 (en) | 2023-11-15 |
| CN115392132B (en) | 2023-07-11 |
| CN115392132A (en) | 2022-11-25 |
| US20230087105A1 (en) | 2023-03-23 |
| EP4151351A1 (en) | 2023-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106205671B (en) | Storage system and its management method | |
| CN101529526B (en) | Method for estimating and reporting the life expectancy of flash-disk memory | |
| US20050234565A1 (en) | Programmable control system for automated actuator operation | |
| WO2019103772A1 (en) | Detection and root cause analysis of welding defects | |
| US7706900B2 (en) | Control apparatus with fast I/O function, and control method for control data thereof | |
| CN103810055A (en) | Programming a non-volatile memory (nvm) system having error correction code (ecc) | |
| CN113779886A (en) | Method, device and system for detecting welding spot quality abnormity based on deep learning | |
| CN116089870A (en) | Industrial equipment fault prediction method and device based on meta-learning under small sample condition | |
| JP2013137845A (en) | Semiconductor memory test method and semiconductor memory | |
| CN111667872A (en) | Method, system, storage medium and terminal device for power-on repair of over-erasure interference | |
| CN112417463A (en) | Software vulnerability prediction method and device, computer equipment and storage medium | |
| US11899561B2 (en) | Method for operating a control unit when testing software of the control unit, and method for operating a test computer when testing software of a control unit | |
| JPWO2020159730A5 (en) | ||
| JP5203724B2 (en) | Insulation resistance tester | |
| CN106910520B (en) | Writing method of storage device, storage controller and storage system | |
| CN108762227B (en) | Automatic driving test system and method | |
| US20070051713A1 (en) | Welding apparatus | |
| CN105868092A (en) | Log file processing method and device | |
| US20210366437A1 (en) | Device state reproduction device, device state reproduction method, and storage medium | |
| JP2017059278A (en) | Semiconductor memory and verification method of semiconductor memory | |
| JP4729179B2 (en) | Memory test method and memory test equipment | |
| JP2009506446A (en) | Data processing system and driving method thereof | |
| CN114720014B (en) | Method and device for detecting pipeline connection in equipment, electronic equipment and storage medium | |
| CN114383860B (en) | Bidirectional fatigue verification method and system for weld joint of vehicle exhaust pipe and electronic equipment | |
| CN117219141A (en) | Method and device for compensating in-memory calculation errors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211210 |
|
| WD01 | Invention patent application deemed withdrawn after publication |